CVE-2026-100654
mediumpriority · track · 26EPSS 0.003 · 24 %ileDEUSEPSS · scored 2026-10-27
vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When min_tokens > 0, the stop token ids are used as logits indices to suppress stop tokens, so an out-of-range id reaches a CUDA indexing operation (index_put_) and triggers a device-side assertion. An authenticated API user can send a single malformed completion request that returns 500 Internal Server Error and puts EngineCore into a fatal state, causing subsequent requests to fail until the service is restarted (denial of service).
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · medium–high · 4.9–7.1
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (3)
Products and version ranges known to be affected.
advisories (1)
Vendor and ecosystem advisories describing this.
- WID-SEC-W-2026-3327vllm: Mehrere Schwachstellen ermöglichenDeutsch2026-09-13csaf · cert_bundDE
Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Sicherheitsvorkehrungen zu umgehen, Daten zu manipulieren, sensible Informationen offenzulegen oder einen Denial-of-Service-Zustand auszulösen.
sources
Which sources assert this record, and when.
references (2) nvd
External citations — patches, advisories, analysis.
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan